Graph neural network outputs are almost surely asymptotically constant

1 code implementation • 6 Mar 2024 • Sam Adam-Day, Michael Benedikt, İsmail İlkan Ceylan, Ben Finkelshtein

Our results apply to a broad class of random graph models, including the (sparse) Erd\H{o}s-R\'enyi model and the stochastic block model.

Stochastic Block Model

Cooperative Graph Neural Networks

no code implementations • 2 Oct 2023 • Ben Finkelshtein, Xingyue Huang, Michael Bronstein, İsmail İlkan Ceylan

Graph neural networks are popular architectures for graph machine learning, based on iterative computation of node representations of an input graph through a series of invariant transformations.

Strategic Classification with Graph Neural Networks

1 code implementation • 31 May 2022 • Itay Eilat, Ben Finkelshtein, Chaim Baskin, Nir Rosenfeld

Strategic classification studies learning in settings where users can modify their features to obtain favorable predictions.

Classification

A Simple and Universal Rotation Equivariant Point-cloud Network

1 code implementation • 2 Mar 2022 • Ben Finkelshtein, Chaim Baskin, Haggai Maron, Nadav Dym

Equivariance to permutations and rigid motions is an important inductive bias for various 3D learning problems.

Inductive Bias

Single-Node Attacks for Fooling Graph Neural Networks

1 code implementation • 6 Nov 2020 • Ben Finkelshtein, Chaim Baskin, Evgenii Zheltonozhskii, Uri Alon

Graph neural networks (GNNs) have shown broad applicability in a variety of domains.

Adversarial Attack